{"model":{"id":"multimodal-audio","name":"Multimodal Audio","description":"NVIDIA Nemotron Omni for audio understanding. Pair an audio clip with a prompt and get a reasoned answer about its contents.","tasks":["vqa","caption","reasoning"],"credits_per_call":4,"input_fields":{"audio_url":"string (required — HTTPS URL to a public audio file)","prompt":"string (required)"},"output_fields":{"result.text":"string"},"api_gross_margin_percent":20,"schema_url":"/api/v1/vision?model_id=multimodal-audio","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/vision?model_id=multimodal-audio","title":"Multimodal Audio request","type":"object","properties":{"model_id":{"type":"string","const":"multimodal-audio"},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"audio_url":{"type":"string","format":"uri"},"prompt":{"type":"string"},"question":{"type":"string"}},"required":["model_id","audio_url"],"anyOf":[{"required":["prompt"]},{"required":["question"]}],"additionalProperties":false}},"version":"1","rate_limit":"20 req/min"}